Convolutional Neural Network Utilizing Error-Correcting Output Codes Support Vector Machine for Classification of Non-Severe Traumatic Brain Injury From Electroencephalogram Signal

Abstract

A sudden blow or jolt to the human brain called traumatic brain injury (TBI) is one of the most common injuries recorded in the health insurance claim. Generally, computed tomography (CT) or magnetic resonance imaging (MRI) is required to identify the trauma's severity. Unfortunately, CT and MRI equipment are bulky, expensive, and not always available, limiting their use in TBI detection. Therefore, as an alternative, this study presents a novel classification architecture that can classify non-severe TBI patients from healthy subjects by using resting-state electroencephalogram (EEG) as the input. The proposed architecture employs a convolutional neural network (CNN), and error-correcting output codes support vector machine (ECOC-SVM) to perform automated feature extraction and multi-class classification. In this architecture, complex feature selection and extraction steps are avoided. The proposed architecture attained a high-performance classification accuracy of 99.76%, potentially being used as a classification approach to preventing healthcare insurance fraud. The proposed method is compared to existing studies in the literature. The outcome from the comparisons indicates that the proposed method has outperformed the benchmarked methods by presenting the highest classification accuracy and precision.

Improving Outcome Prediction for Traumatic Brain Injury From Imbalanced Datasets Using RUSBoosted Trees on Electroencephalography Spectral Power

“…Enschede, Netherlands) at a sampling rate of 1000 Hz. The WaveGuard TM Original EEG head cap with gel-based electrodes was employed according to the international layout of 10-10 electrode system for electrode placement [69], as shown in Figure 2.…”

“…Data pre-processing was carried out using the EEGLAB v2019.0, an open source software [71] running on MATLAB (Mathworks Inc. R2020a) with the custom MATLAB code. In the first step, the power line noise was removed by applying a notch filter at 50 Hz (in Malaysia) [69] with the pop_eegfiltnew () function of EEGLAB to the signal r. The resting-state EEG recording with eyes-closed aided in the reduction of rapid eye movement (i.e., blinking and visual fatigue) [72]. Next, a small number of blink-like signal shapes and muscular activity were manually selected and removed [29].…”

Diastolic Dysfunction Prediction with Symptoms Using Machine Learning Approach

“…SVM is a mathematically based algorithm for creating a model for data analysis. The SVM algorithm is rapidly used in machine learning studies for better classification [40][41][42]. J.48 Algorithm.…”

Vision-Based Malware Detection: A Transfer Learning Approach Using Optimal ECOC-SVM Configuration

“…ECOC ensemble has been proposed in many areas to improve the classification performance. For example, in [15], it was shown that 99.7% recognition can be achieved using CNN-ECOC for the case of brain tumor detection. Similarly, for skin cancer detection [16], AlexNet, a pre-trained CNN model, was used to extract the features.…”